Jump to content

  • Log In with Google      Sign In   
  • Create Account

We're offering banner ads on our site from just $5!

1. Details HERE. 2. GDNet+ Subscriptions HERE. 3. Ad upload HERE.


alexjc

Member Since 13 Feb 2001
Offline Last Active Feb 13 2014 06:07 AM

#5131019 Game/AI Conf. 2014: Early Bird & Call for Speakers (July 7th-10th)

Posted by alexjc on 13 February 2014 - 06:08 AM

The Game/AI Conference 2014 will take place on July 7th to 10th, in Vienna/Austria.

 

 

CALL FOR SPEAKERS

 

CallForProposals_Header-304x174.jpg

 

Whether you're a professional working in the games industry, or a researcher in artificial

intelligence, speaking at the conference is a fantastic experience.  So if you have a proposal,

of course we'd love to hear it!

 

Send your email to <events at aigamedev.com>, or consider reading more about it here:

 

    http://gameaiconf.com/highlight/call-for-speakers-volunteers/

 

 

If you have any questions (or ideas) for the conference, don't hesitate to let us know!

 

 

EARLY BIRD TICKETS

 

AkademieDerWissenshaften.wide_-304x174.j

 

We're very pleased to announce that the event this year will take place at the prestigious

Austrian Academy of Sciences, a magnificent and historical building.  It's located at the

heart of Vienna's 1st district, equally amazing for both tourism and game conferences!

 

    http://gameaiconf.com/highlight/2014-confirmed/

 
 

Tickets are available now.  You can secure a 50% discount if you buy now (and not for

much longer), or if you're a student just email us <events at aigamedev.com> and we'll

send you the details for a specially priced ticket!

 

 

Alex

 




#5052078 Dealing with multiple threats in a BT framework

Posted by alexjc on 11 April 2013 - 06:02 AM

Hi,

 

Good question!

 

In general this problem is independent of how you execute the behaviors.  Most often, there's a separate system for picking the highest risk target and engage a single behavior to deal with that, there's a separate system for picking positions according to that primary target (and possibly a secondary one), etc.

 

I've rarely seen production systems take into account more than two threats for position picking, and even in the cases you have two threats, the second tends to be weighted a bit lower than the first to prevent indecision problems and static/boring gameplay.

 

Alex




#4979239 Game/AI Conference 2012

Posted by alexjc on 12 September 2012 - 03:50 AM

The Live Stream from the Vienna Game/AI Conference will be available online free. By this time next week, Day #2 will already be underway. The broadcast starts around 07:00 UTC.

I hope you can join us live to interact with the presenters and the attendees!


#4967275 Papers on RVO/HRVO?

Posted by alexjc on 08 August 2012 - 12:53 AM

First of all, thanks for taking the time to formulate a great question! It stands out among most others here :-)

I haven't worked with RVO2, so I'm not sure why it's taking that branch. However, a few things may help:
  • ORCA is a bit easier to understand from the perspective of the "solver" -- it's just linear programming.
  • Some algorithms have biases for turning in a particular direction, so it may be on purpose.
  • ORCA for instance completely rules out half of the search space, which would similar to what you're seeing.
Have you tried drawing the velocity obstacles? See this screenshot I tweeted recently from last weekend's AiGameDev interview. The green planes are what ORCA gets as input, and the red circles (less obvious) are the velocity obstacle. It does make sense visually so you should be getting something that looks reasonable.

Alex

P.S. There's also a masterclass on the topic with Jamie Snape on AiGameDev but it sounds like you're almost there :-)


#4965533 How to calculate Velocity Obstacle?

Posted by alexjc on 02 August 2012 - 08:40 AM

I won't help with your implementation directly, RVO are very well documented. Here's my best advice:
  • If you want a quick solution, use the available libraries such as RVO2.
  • If you want to implement it yourself, go through the papers. This one isn't a bad place to start.
I hope that helps get you started!

Alex


#4964809 implimenting AI elegantly

Posted by alexjc on 31 July 2012 - 05:22 AM

I'd agree with Alvaro's advice. I've found utility very suited to managing relatively simple decisions (limited number of outputs) from arbitrary information (large number of inputs). There was a lecture at the AI Summit by Kevin Dill and he emphasized the modularity of input "criteria" above all. I asked him about modularity of decisions/output and he said something like: "Sure, for that you need a BT-style structure."

If you have large numbers of possible outputs, and want to express a large variety of special cases that can combine together, then behavior trees or hierarchical planners are my recommended option. Utility has been found not to scale up very well in these areas (e.g. performance), and games like the SIMS 3 famously moved away from "utility everywhere" for these reasons.

Alex


#4964800 Game/AI Conference 2012

Posted by alexjc on 31 July 2012 - 04:41 AM

The Vienna Game/AI Conference 2012 is the largest independent event dedicated to artificial intelligence, gameplay and character animation. Last year it brought together over 300 developers from around the world, including programmers from the leading European studios such as IO Interactive, Rocksteady, 2K Czek, Splash Damage, Ubisoft – and many more.


This year, most sessions have been officially announced and the full schedule will follow, including the following titles:
  • BATMAN: ARKHAM CITY from Rocksteady Studios
  • HITMAN: ABSOLUTION from IO Interactive
  • GRiD & F1 from Codemasters
  • SPEC OPS: THE LINE from Yager Development
  • VESSEL from Strange Loop Games
  • MAFIA 2 from 2K Czek
  • MOTORSTORM: APOCALYPSE from Evolution Studios
There are also some tutorials (included in main conference) and workshops (standalone) on the topics of:
  • Procedural Character Animation Workshop
  • Behavior Tree Logic Workshop
  • Monte Carlo Tree Search (MCTS)
  • Data-Mining and Pattern Recognition
Tickets are available from 96€ for the next few weeks, and if you're a student we have a handful of Bronze tickets at 48€. Keep an eye on the official website or @GameAiConf on Twitter for details. If you have any questions don't hesitate to ask!

Alex Champandard


#4954800 time-slicing or multithreading for pathfinding?

Posted by alexjc on 02 July 2012 - 12:35 AM

What are your requirements?

In many situations you should need neither for the following reasons :-)
  • Time-slicing implies your pathfinding requests take longer than a frame. Best optimize them or use an algorithm that fits comfortably within a frame. Then do an integer number of them each frame.
  • Multi-threaded pathfinding is used on PS3, but often on XBox360 or PC there's a separate (single) thread for pathfinding.
Keep in mind that either of these choices can result in your AI being much less deterministic if you're not very careful!

Alex


#4953752 C# AStar

Posted by alexjc on 28 June 2012 - 02:28 PM

Assuming you're doing this for learning purposes, and not reusing an existing piece of code... My best advice is to write some unit tests incrementally and check all your assumptions. I've found that unit tests provide amazing support for learning new algorithms, languages, and writing new code in general :-)

I realize you wanted someone to debug your program but well... ;-)


#4947457 Behavior Tree Traversal

Posted by alexjc on 08 June 2012 - 01:36 PM

If you have a tree without parallel nodes, then you only need to store a single pointer to "cache" a node and just update that. Otherwise you need a more fully featured event-driven BT implementation.

See more here, I did a 1h presentation on the topic of BTs, starting simple and then moving into second-gen trees (such as the event-driven ones):
http://aigamedev.com/insider/tutorial/second-generation-bt/

Alex


#4917528 Behavior Trees vs Hiearichal Task Networks

Posted by alexjc on 28 February 2012 - 04:18 PM

A HTN is actually searched ahead of the current behavior, so it's not just a best-first search it goes the full tree if necessary. You'll need backtracking to implement an HTN planner, and the result will be a list of actions that are not executed by the planner, but passed back for you to execute yourself.

Look into SHOP, it's a well documented HTN planner with source code.

Alex
AiGameDev.com


#4801597 Picking question

Posted by alexjc on 22 April 2011 - 06:46 AM

What do you mean by picking? A ray / polygon intersection test? What are you trying to do?

Alex

P.S. You might want to read this for future reference.


#4790128 Game/AI Conference 2011

Posted by alexjc on 24 March 2011 - 03:17 PM

The Paris Game/AI Conference 2011 is the largest independent event dedicated to artificial intelligence, gameplay and character animation. Last year it brought together almost 300 developers from around the world, including programmers from the leading European studios such as DICE, Guerrilla Games, Quantic Dream, CCP Games, Ubisoft and many more.

This year, the first few speakers have been announced, including:
  • Torsten Reil from Natural Motion, talking about euphoria and its application to BACKBREAKER.
  • Mikko Mononen the open-source wizzard, demonstrating how he applied Recast into KILLZONE 3.
  • Eskil Steenberg, the one-man show behind LOVE (the MMO) about the new AI in the game.
  • Ingnimar Gudmunsson, Battle AI Programmer at the Creative Assembly, on TOTAL WAR: SHOGUN 2.
  • Neil Henning, Technical Lead at Codeplay, about optimizing the AI of NASCAR, THE GAME 2011.
  • Giliam de Carpenter, AI Programmer at Vanguard, telling the story behind the AI in GREED CORP.
  • ... (more to follow shortly)
Tickets are available from 96€ or 48€ if you're a student (just email us to setup your discount). Keep an eye on the official website or @GameAiConf on Twitter for details. If you have any questions don't hesitate to ask!


Alex Champandard


#4614364 any neural network experts?

Posted by alexjc on 06 March 2010 - 01:25 AM

Back propagation is surprisingly robust if you let it train for ages, more so than other training algorithms.

However, I've had a lot of success with things like RPROP. The idea is to batch up all the weight deltas while training, so you're less likely to find local minima.

It's not too much work to implement. See the FANN library if you get stuck.



#4538441 questions about FuSM implementation

Posted by alexjc on 08 October 2009 - 03:23 AM

Most places/tutorials get fuzzy finite state machines completely confused.

Most often they mean a probabilistic finite state machine, which means you throw a dice randomly and pick a transition based on that. You could also use fuzzy logic to rank the different transition options for each state, and then pick the best transition.

However, technically a fuzzy finie state machine (FFSM) has all the states "active" at once. Then you calculate the next value of each state by going through all transitions and propagating the value of each previous state. So it becomes very much like a neural network, and there are loads of great papers about this.


Though, most likely what you want is a probabilistic finite state machine :-)





PARTNERS